High-throughput detection of prostate cancer in histological sections using probabilistic pairwise Markov models.
High-throughput detection of prostate cancer in histological sections using probabilistic pairwise Markov models.
复制标题
DOI：
10.1016/j.media.2010.04.007
复制
发表时间：
2010-08
影响因子：
10.9
通讯作者：
Madabhushi, Anant
中科院分区：
文献类型：
--
作者：
Monaco, James P.;Tomaszewski, John E.;Feldman, Michael D.;Hagemann, Ian;Moradi, Mehdi;Mousavi, Parvin;Boag, Alexander;Davidson, Chris;Abolmaesumi, Purang;Madabhushi, Anant
在本文中，我们提出了一个高通量的系统，用于检测区域的前列腺癌（CaP）在HS从根治性前列腺切除术（RP）使用概率成对马尔可夫模型（PPMM），一种新型的马尔可夫随机场（MRF）。在诊断分辨率下，数字化HS可以包含80 K × 70 K像素-对于当前的自动格里森分级算法来说太多了。然而，分级可以分为两个不同的步骤：1）检测癌区域和2）然后对这些区域进行分级。检测步骤不需要诊断分辨率，并且可以更快地执行。因此，我们引入了一种CaP检测系统，该系统能够在三分钟内（在台式计算机上）分析整个数字化整装HS（2×1.75 cm 2），同时分别实现0.87和0.90的CaP检测灵敏度和特异性。我们通过定制系统以低分辨率（每像素8 µm）分析HS来获得这种高通量。这激发了以下算法：步骤1）腺体被分割，步骤2）分割的腺体被分类为恶性或良性，以及步骤3）恶性腺体被合并成连续区域。单个腺体的分类利用了两个特征：腺体大小和邻近腺体共享同一类的趋势。后一个功能描述了一个空间依赖性，我们使用马尔可夫先验模型。通常，马尔可夫先验被表示为势函数的乘积。不幸的是，潜在的功能是数学抽象，并通过他们的选择构建先验成为一个特设的程序，导致简单的模型，如波茨。为了解决这个问题，我们引入了PPMM，它根据概率密度函数制定先验，从而可以创建更复杂的模型。为了证明我们的CaP检测系统的有效性，并评估使用PPMM先验而不是Potts的优势，我们交替地将这两个先验纳入我们的算法，并严格评估系统性能，从40个RP标本的6000多个模拟中提取统计数据。也许最具指示性的结果如下：在0.87的CaP灵敏度下，当交替采用PPMM和Potts先验时，系统的伴随假阳性率分别为0.10和0.20。
In this paper we present a high-throughput system for detecting regions of carcinoma of the prostate (CaP) in HSs from radical prostatectomies (RPs) using probabilistic pairwise Markov models (PPMMs), a novel type of Markov random field (MRF). At diagnostic resolution a digitized HS can contain 80K×70K pixels — far too many for current automated Gleason grading algorithms to process. However, grading can be separated into two distinct steps: 1) detecting cancerous regions and 2) then grading these regions. The detection step does not require diagnostic resolution and can be performed much more quickly. Thus, we introduce a CaP detection system capable of analyzing an entire digitized whole-mount HS (2×1.75 cm2) in under three minutes (on a desktop computer) while achieving a CaP detection sensitivity and specificity of 0.87 and 0.90, respectively. We obtain this high-throughput by tailoring the system to analyze the HSs at low resolution (8 µm per pixel). This motivates the following algorithm: Step 1) glands are segmented, Step 2) the segmented glands are classified as malignant or benign, and Step 3) the malignant glands are consolidated into continuous regions. The classification of individual glands leverages two features: gland size and the tendency for proximate glands to share the same class. The latter feature describes a spatial dependency which we model using a Markov prior. Typically, Markov priors are expressed as the product of potential functions. Unfortunately, potential functions are mathematical abstractions, and constructing priors through their selection becomes an ad hoc procedure, resulting in simplistic models such as the Potts. Addressing this problem, we introduce PPMMs which formulate priors in terms of probability density functions, allowing the creation of more sophisticated models. To demonstrate the efficacy of our CaP detection system and assess the advantages of using a PPMM prior instead of the Potts, we alternately incorporate both priors into our algorithm and rigorously evaluate system performance, extracting statistics from over 6000 simulations run across 40 RP specimens. Perhaps the most indicative result is as follows: at a CaP sensitivity of 0.87 the accompanying false positive rates of the system when alternately employing the PPMM and Potts priors are 0.10 and 0.20, respectively.
登录
查看更多内容
影响因子：
10.6
作者：
Farag, AA;El-Baz, AS;Gimel'farb, G
通讯作者：
Gimel'farb, G
影响因子：
10.6
作者：
Huang, Po-Whei;Lee, Cheng-Hsiung
通讯作者：
Lee, Cheng-Hsiung
影响因子：
4.6
作者：
Jafari-Khouzani, K;Soltanian-Zadeh, H
通讯作者：
Soltanian-Zadeh, H
影响因子：
23.4
作者：
Heidenreich, Axel;Aus, Gunnar;Zattoni, Filliberto
通讯作者：
Zattoni, Filliberto
影响因子：
10.6
作者：
LI, HD;KALLERGI, M;CLARK, RA
通讯作者：
CLARK, RA